It is common in computer vision to be confronted with domain shift: images which have the same class but different acquisition conditions. In domain adaptation (DA), one wants to classify unlabeled target images using source labeled images. Unfortunately, deep neural networks trained on a source training set perform poorly on target images which do not belong to the training domain. One strategy to improve these performances is to align the source and target image distributions in an embedded space using optimal transport (OT). However OT can cause negative transfer, i.e. aligning samples with different labels, which leads to overfitting especially in the presence of label shift between domains. In this work, we mitigate negative alignment by explaining it as a noisy label assignment to target images. We then mitigate its effect by appropriate regularization. We propose to couple the MixUp regularization \citep{zhang2018mixup} with a loss that is robust to noisy labels in order to improve domain adaptation performance. We show in an extensive ablation study that a combination of the two techniques is critical to achieve improved performance. Finally, we evaluate our method, called \textsc{mixunbot}, on several benchmarks and real-world DA problems.
翻译:在计算机视野中,常见的情况是面对域变:具有相同等级但不同的获取条件的图像。在域变换(DA)中,人们希望使用源标签图像对未贴标签的目标图像进行分类。 不幸的是,在源培训的深神经网络在不属于培训域的目标图像上表现不佳。 改进这些性能的一种策略是利用最佳运输(OT)使源和目标图像在嵌入空间中分布相匹配。 但是,OT可以造成负转移, 即将样本与不同标签相匹配, 特别是在存在域间标签变化的情况下, 导致过度配对。 在这项工作中, 我们通过对目标图像进行响亮的标签分配来减少负对齐。 我们随后通过适当的正规化来减轻其效果。 我们提议将MixUp manging \citep{zhang2018mup} 与一个能够振动标签以改进域适应性能的亏损同时进行。 我们通过一个广泛的模拟研究显示, 两种技术的组合对于改进性能至关重要。 最后, 我们评估了我们的方法, 称为\ mixc{mixunbotbot}